Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Meta Reinforcement Learning on Ant-dir (out-of-distribution)
Loading...
410.7
Average Return
SPC
146.644
215.197
283.75
352.303
Mar 3, 2026
Average Return
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Return
SPC
Zero-shot=true
2026.03
410.7
UNICORN-SS
Zero-shot=true
2026.03
405.9
CSRO
Zero-shot=true
2026.03
399.2
FOCAL
Zero-shot=true
2026.03
368.8
UNICORN-SUP
Zero-shot=true
2026.03
211.4
DORA
Zero-shot=true
2026.03
156.8
Feedback
Search any
task
Search any
task